{"id":"https://openalex.org/W7131129552","doi":"https://doi.org/10.1109/access.2026.3667399","title":"Improving Contextual Biasing in Chinese ASR via Multimodal Large Language Models","display_name":"Improving Contextual Biasing in Chinese ASR via Multimodal Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131129552","doi":"https://doi.org/10.1109/access.2026.3667399"},"language":null,"primary_location":{"id":"doi:10.1109/access.2026.3667399","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3667399","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3667399","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126585875","display_name":"Kai Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Zhang","raw_affiliation_strings":["Yiwu Industrial and Commercial College, Yiwu, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0004-1688-1815","affiliations":[{"raw_affiliation_string":"Yiwu Industrial and Commercial College, Yiwu, Zhejiang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101582282","display_name":"Qiuxia Zhang","orcid":"https://orcid.org/0009-0003-2560-4038"},"institutions":[{"id":"https://openalex.org/I4210119757","display_name":"Jinhua Academy of Agricultural Sciences","ror":"https://ror.org/02n6fv369","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210119757"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuxia Zhang","raw_affiliation_strings":["Zhejiang Commerce and Trade School, Jinhua Open University, Jinhua, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Commerce and Trade School, Jinhua Open University, Jinhua, Zhejiang, China","institution_ids":["https://openalex.org/I4210119757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016475945","display_name":"Chung-Che Wang","orcid":"https://orcid.org/0000-0002-1414-9848"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Che Wang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-1414-9848","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120398738","display_name":"Jyh-Shing Roger Jang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jyh-Shing Roger Jang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-7319-9095","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2375859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"29706","last_page":"29728"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.34209999442100525,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.34209999442100525,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1881999969482422,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.15440000593662262,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6840999722480774},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5658000111579895},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.557200014591217},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5357999801635742},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5074999928474426},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4577000141143799},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4345000088214874},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3912000060081482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8707000017166138},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6840999722480774},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5658000111579895},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.557200014591217},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5357999801635742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5220999717712402},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5199999809265137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5192999839782715},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5074999928474426},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3508000075817108},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3472000062465668},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.32519999146461487},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3248000144958496},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C71611378","wikidata":"https://www.wikidata.org/wiki/Q5165191","display_name":"Contextual design","level":3,"score":0.2734000086784363},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2026.3667399","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3667399","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3667399","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3667399","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6171494722366333,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6271462199","display_name":null,"funder_award_id":"24-3-160","funder_id":"https://openalex.org/F4320336651","funder_display_name":"Quanzhou City Science and Technology Program"}],"funders":[{"id":"https://openalex.org/F4320336651","display_name":"Quanzhou City Science and Technology Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"addresses":[2],"the":[3,57,93,108,152,208,238],"challenge":[4],"in":[5,131,148,203,227,245],"Chinese":[6,228],"automatic":[7],"speech":[8,121,183,247],"recognition":[9,250],"(ASR)":[10],"systems":[11],"of":[12,66,169,210,240],"accurately":[13],"recognizing":[14],"proper":[15,170],"nouns":[16,171],"such":[17],"as":[18],"place":[19],"names,":[20,22],"personal":[21],"song":[23],"titles,":[24,30],"and":[25,38,61,96,137,230,235,249],"movie":[26],"or":[27],"TV":[28],"show":[29,190],"which":[31],"is":[32,69],"often":[33],"hindered":[34],"by":[35,182],"tonal":[36],"features":[37],"abundant":[39],"homophones.":[40],"We":[41],"propose":[42],"an":[43,70,85,158,221],"integrated":[44],"contextual":[45,73,225],"biasing":[46,74,226],"framework":[47,68,223],"centered":[48],"on":[49,107,213],"multimodal":[50,241],"large":[51,242],"language":[52,179,243],"models":[53,192,211,244],"(MLLMs)":[54],"to":[55,92,101,119,172,185],"enhance":[56],"system\u2019s":[58],"context":[59],"awareness":[60],"task":[62],"adaptability.":[63],"The":[64],"core":[65],"this":[67,126,218],"intent-driven":[71],"dynamic":[72],"mechanism:":[75],"first,":[76],"a":[77,97,102,143,166,177,198],"fine-tuned":[78,124,193],"MLLM":[79],"performs":[80],"end-to-end":[81],"intent":[82,111],"recognition,":[83,205],"achieving":[84],"81.82%":[86],"relative":[87,100,145,200],"error":[88,134,139,146,201],"rate":[89,135,140],"reduction":[90,99,147,202],"compared":[91],"unfine-tuned":[94],"model":[95],"66.71%":[98],"cascaded":[103],"model;":[104],"subsequently,":[105],"based":[106],"highly":[109],"accurate":[110],"predictions,":[112],"context-relevant":[113],"keyword":[114,138,204],"prompts":[115],"are":[116],"dynamically":[117],"generated":[118],"guide":[120],"recognition.":[122],"Models":[123],"using":[125,176],"strategy":[127],"demonstrate":[128],"significant":[129],"improvements":[130],"both":[132],"character":[133],"(CER)":[136],"(KER),":[141],"with":[142,194],"41.48%":[144],"KER.":[149],"To":[150],"address":[151],"cold-start":[153],"problem,":[154],"we":[155],"also":[156],"develop":[157],"automated":[159],"data":[160,196],"generation":[161],"pipeline":[162],"that":[163,191],"requires":[164],"only":[165],"domain-specific":[167],"list":[168],"generate":[173],"natural":[174],"sentences":[175],"small":[178],"model,":[180],"followed":[181],"synthesis":[184],"produce":[186],"training":[187],"audio.":[188],"Experiments":[189],"synthetic":[195],"achieve":[197],"41.91%":[199],"nearly":[206],"matching":[207],"performance":[209],"trained":[212],"real":[214],"annotated":[215],"data.":[216],"Overall,":[217],"work":[219],"provides":[220],"innovative":[222],"for":[224],"ASR":[229],"demonstrates,":[231],"through":[232],"open-source":[233],"code":[234],"evaluation":[236],"standards,":[237],"potential":[239],"integrating":[246],"understanding":[248],"tasks.":[251]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-24T00:00:00"}